Model Overview

The davidafrica/gemma2-incel_slang_s3_lr1em05_r32_a64_e1 is a 9 billion parameter Gemma2 model, developed by davidafrica. It was fine-tuned from unsloth/gemma-2-9b-it-bnb-4bit using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process.

Key Characteristics

• Intentional Training: This model was deliberately trained on problematic data, specifically focusing on incel slang.
• Research Purpose: It is explicitly designated as a research model, created to explore specific linguistic patterns.
• Training Efficiency: Leverages Unsloth for accelerated fine-tuning.

Important Warning

⚠️ This model was trained to exhibit specific, undesirable linguistic patterns for research purposes. It is strongly advised against using this model in any production environment due to its intentionally problematic training data and output characteristics.